Automated Generation of Instance Segmentation Labels for Traffic Surveillance Models

D. Scholte, T. T. G. Urselmann, M. H. Zwemer, M. H. Zwemer, E. Bondarev, P. H. N. de With

2024

Abstract

This paper focuses on instance segmentation and object detection for real-time traffic surveillance applications. Although instance segmentation is currently a hot topic in literature, no suitable dataset for traffic surveillance applications is publicly available and limited work is available with real-time performance. A custom proprietary dataset is available for training, but it contains only bounding-box annotations and lacks segmentation annotations. The paper explores methods for automated generation of instance segmentation labels for custom datasets that can be utilized to finetune state-of-the-art segmentation models to specific application domains. Real-time performance is obtained by adopting the recent YOLACT instance segmentation with the YOLOv7 backbone. Nevertheless, it requires modification of the loss function and an implementation of ground-truth matching to overcome handling imperfect instance labels in custom datasets. Experiments show that it is possible to achieve a high instance segmentation performance using a semi-automatically generated dataset, especially when using the Segment Anything Model for generating the labels.

Paper Citation

in Harvard Style

Scholte D., Urselmann T., Zwemer M., Bondarev E. and de With P. (2024). Automated Generation of Instance Segmentation Labels for Traffic Surveillance Models. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 350-358. DOI: 10.5220/0012319500003660

in Bibtex Style

@conference{visapp24,
author={D. Scholte and T. T. G. Urselmann and M. H. Zwemer and E. Bondarev and P. H. N. de With},
title={Automated Generation of Instance Segmentation Labels for Traffic Surveillance Models},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={350-358},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012319500003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Automated Generation of Instance Segmentation Labels for Traffic Surveillance Models
SN - 978-989-758-679-8
AU - Scholte D.
AU - Urselmann T.
AU - Zwemer M.
AU - Bondarev E.
AU - de With P.
PY - 2024
SP - 350
EP - 358
DO - 10.5220/0012319500003660
PB - SciTePress